Fast and Memory Optimal Low-Rank Matrix Approximation

Yun Se-Young 1, 2 Marc Lelarge 3, 2, * Alexandre Proutière 4
* Auteur correspondant
2 DYOGENE - Dynamics of Geometric Networks
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : In this paper, we revisit the problem of constructing a near-optimal rank k approximation of a matrix M ∈ [0, 1] m×n under the streaming data model where the columns of M are revealed sequentially. We present SLA (Streaming Low-rank Approximation), an algorithm that is asymptotically accurate, when ks k+1 (M) = o(√ mn) where s k+1 (M) is the (k + 1)-th largest singular value of M. This means that its average mean-square error converges to 0 as m and n grow large (i.e., ˆ M (k) −M (k) 2 F = o(mn) with high probability, wherê M (k) and M (k) denote the output of SLA and the optimal rank k approximation of M , respectively). Our algorithm makes one pass on the data if the columns of M are revealed in a random order, and two passes if the columns of M arrive in an arbitrary order. To reduce its memory footprint and complexity, SLA uses random sparsification, and samples each entry of M with a small probability δ. In turn, SLA is memory optimal as its required memory space scales as k(m+n), the dimension of its output. Furthermore, SLA is computationally efficient as it runs in O(δkmn) time (a constant number of operations is made for each observed entry of M), which can be as small as O(k log(m) 4 n) for an appropriate choice of δ and if n ≥ m.
Type de document :
Communication dans un congrès
NIPS 2015, Dec 2015, Montreal, Canada
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01254913
Contributeur : Marc Lelarge <>
Soumis le : mardi 12 janvier 2016 - 18:41:45
Dernière modification le : mardi 11 décembre 2018 - 01:23:52
Document(s) archivé(s) le : vendredi 11 novembre 2016 - 03:14:15

Fichier

5929-fast-and-memory-optimal-l...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01254913, version 1

Citation

Yun Se-Young, Marc Lelarge, Alexandre Proutière. Fast and Memory Optimal Low-Rank Matrix Approximation. NIPS 2015, Dec 2015, Montreal, Canada. 〈hal-01254913〉

Partager

Métriques

Consultations de la notice

387

Téléchargements de fichiers

259